Topic
audio deepfake detection
Artificial Intelligence #flowfake#liquid networks
FlowFake: Liquid Time-Constant Architecture Boosts Audio Deepfake Detection Cross-Dataset Generalization
FlowFake, a new audio deepfake detector using Liquid Time-Constant networks, achieves 75-80% accuracy on cross-dataset benchmarks with only 34K parameters, matching models 300x larger. It addresses the critical cross-dataset generalization problem threatening speaker verification systems.
Jun 20, 2026 1 source
Artificial Intelligence #audio deepfake detection#disentanglement
Dual-Granularity Orthogonal Disentanglement: New Framework Boosts Generalizable Audio Deepfake Detection
A new paper on arXiv proposes a dual-granularity orthogonal disentanglement framework for generalizable audio deepfake detection. The method enforces sample-level cosine orthogonality and batch-level cross-covariance regularization to avoid speaker identity leakage. Experiments show equal error rates of 1.35%, 7.88%, and 21.58% on standard benchmarks.
Jun 16, 2026 1 source